The four heights
The same task, four distances: today's deadline, the next reviewer, the stuck moment, the pattern.
Execute — do the immediate task
+I have appropriation details for emergency funding items and broader program budgets. Send matched…
Execute — do the immediate task
+I have appropriation details for emergency funding items and broader program budgets. Send matched entries to the grants manager and the CFO for alignment and approval, in that order, with a Tuesday deadline — verify each emergency item is correctly mapped to its broader program before you send.
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Improve — make it easier to accept
+Before I send the matching to the grants office, make it easy to accept: show a short table linking…
Improve — make it easier to accept
+Before I send the matching to the grants office, make it easy to accept: show a short table linking each emergency appropriation to the broader program, surface any mismatches, and flag items lacking authorization or that would trigger reallocation rules. Put the totals that matter to the CFO up front.
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Decide — diagnose the stuck moment
+I tried to match emergency fund items to program appropriations and found five transactions that…
Decide — diagnose the stuck moment
+I matched emergency items but found several that don’t map cleanly to a parent appropriation.
I tried to match emergency fund items to program appropriations and found five transactions that don’t map cleanly. The grants manager, Sofia, worries about audit exceptions; the CFO, Mark, will demand a clean trail. I don’t know whether those items were miscoded or legitimately charged. What is the likely diagnosis and the best next step to avoid an audit finding?
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Become — change the pattern
+We keep getting audit findings from emergency items miscoded against broader programs because…
Become — change the pattern
+We repeatedly have miscoded emergency items that blow reconciliations and audits.
We keep getting audit findings from emergency items miscoded against broader programs because entries are rushed and coding rules are unclear. This consumes reconciliation time and risks penalties. What single change in how we collect approvals or code emergency spend would stop the recurring errors?
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Where the evidence lives
Who was seen doing this, and what people really ask.
Software tasks in the LLOS Work Atlas come from evidence, never a feature list: careers attested to do the work, real job descriptions, and the questions people actually ask (with their view counts). Facets — feature, workflow, troubleshoot, administer, deploy, scale — are open metadata: the work decides, not a taxonomy.
Copyright © LLOS.ai · 2026 — original pedagogy, voice, and design — all rights reserved.
The rest of the map
Same library, five ways in.